Performance of a multi-biomarker panel for prediction of cardiovascular event in patients with chronic kidney disease

Machine learning model for cardiovascular disease prediction in patients with chronic kidney disease

Introduction

Cardiovascular disease (CVD) is the leading cause of death in patients with chronic kidney disease (CKD). This study aimed to develop CVD risk prediction models using machine learning to support clinical decision making and improve patient prognosis.

Methods

Electronic medical records from patients with CKD at a single center from 2015 to 2020 were used to develop machine learning models for the prediction of CVD. Least absolute shrinkage and selection operator (LASSO) regression was used to select important features predicting the risk of developing CVD. Seven machine learning classification algorithms were used to build models, which were evaluated by receiver operating characteristic curves, accuracy, sensitivity, specificity, and F1-score, and Shapley Additive explanations was used to interpret the model results. CVD was defined as composite cardiovascular events including coronary heart disease (coronary artery disease, myocardial infarction, angina pectoris, and coronary artery revascularization), cerebrovascular disease (hemorrhagic stroke and ischemic stroke), deaths from all causes (cardiovascular deaths, non-cardiovascular deaths, unknown cause of death), congestive heart failure, and peripheral artery disease (aortic aneurysm, aortic or other peripheral arterial revascularization). A cardiovascular event was a composite outcome of multiple cardiovascular events, as determined by reviewing medical records.

Results

This study included 8,894 patients with CKD, with a composite CVD event incidence of 25.9%; a total of 2,304 patients reached this outcome. LASSO regression identified eight important features for predicting the risk of CKD developing into CVD: age, history of hypertension, sex, antiplatelet drugs, high-density lipoprotein, sodium ions, 24-h urinary protein, and estimated glomerular filtration rate. The model developed using Extreme Gradient Boosting in the test set had an area under the curve of 0.89, outperforming the other models, indicating that it had the best CVD predictive performance.

Conclusion

This study established a CVD risk prediction model for patients with CKD, based on routine clinical diagnostic and treatment data, with good predictive accuracy. This model is expected to provide a scientific basis for the management and treatment of patients with CKD.

Development of multiple biomarker panels for prediction of sarcopenia in community-dwelling older adults

BACKGROUND

It is required to consider multiple biomarkers simultaneously to predict sarcopenia and to understand its complex pathological mechanisms. This study aimed to develop multiple biomarker panels for predicting sarcopenia in older adults and to further examine its association with the incidence of sarcopenia.

METHODS

A total of 1,021 older adults were selected from the Korean Frailty and Aging Cohort Study. Sarcopenia was defined by the Asian Working Group for Sarcopenia 2019 criteria. Among the 14 biomarker candidates at baseline, eight biomarkers that could optimally detect individuals with sarcopenia were selected to develop a multi-biomarker risk score (range from 0 to 10). The utility of developed multi-biomarker risk score in discriminating sarcopenia was investigated using receiver operating characteristic (ROC) analysis.

RESULTS

The multi-biomarker risk score had an area under the ROC curve (AUC) of 0.71 with an optimal cut-off of 1.76 score, which was significantly higher than all single biomarkers with AUC of <0.7 (all, p<0.01). During the two-year follow-up, the incidence of sarcopenia was 11.1%. Continuous multi-biomarker risk score was positively associated with incidence of sarcopenia after adjusting confounders (odds ratio [OR]=1.63; 95% confidence interval [CI]=1.23-2.17). Participants with a high risk score had higher odds of sarcopenia than those with a low risk score (OR=1.82; 95% CI=1.04-3.19).

CONCLUSIONS

Multi-biomarker risk score, which was a combination of eight biomarkers with different pathophysiologies, better discriminated the presence of sarcopenia than a single biomarker, and it could further predict the incidence of sarcopenia over two years in older adults.